adb_shell · Adb MCP: Risk & Policy

WHAT IT DOES

What adb_shell does on Adb

AI agents invoke adb_shell to trigger actions in Adb. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why adb_shell needs a policy

This tool executes arbitrary shell commands on a remote Android device with effects entirely dependent on what command an agent chooses to run. This is the definition of Execute category. The severity is critical because shell access to an Android device enables nearly unrestricted system-level operations, data exfiltration, malware installation, and destructive actions.

From the tool's definition Tool description: 'Run a shell command on the device via ADB.' Shell commands on Android devices can perform virtually any operation including accessing sensitive data, modifying system settings, installing malware, exfiltrating files, or bricking the device…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

adb_shell Rate-limited

adb_shell stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "adb_shell": {
      "limits": [
        {
          "counter": "adb_shell_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Adb, so you can run agents against it safely.

FAQ

Questions about adb_shell

What does the adb_shell tool do? +

Run a shell command on the device via ADB. Returns stdout, stderr, and exit code. Output is truncated at 100KB. It is categorised as a Execute tool in the Adb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on adb_shell? +

Register the Adb MCP server in PolicyLayer and add a rule for adb_shell: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Adb. Nothing to install.

What risk level is adb_shell? +

adb_shell is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit adb_shell? +

Yes. Add a rate_limit block to the adb_shell rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block adb_shell completely? +

Set action: deny in the PolicyLayer policy for adb_shell. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides adb_shell? +

adb_shell is provided by the Adb MCP server (sfaizi24/adb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.